Pub Date : 2024-04-14DOI: 10.1109/icassp48485.2024.10446187
Cheng Cheng, Ziping Zhao
{"title":"Accelerating Gradient Descent for Over-Parameterized Asymmetric Low-Rank Matrix Sensing via Preconditioning","authors":"Cheng Cheng, Ziping Zhao","doi":"10.1109/icassp48485.2024.10446187","DOIUrl":"https://doi.org/10.1109/icassp48485.2024.10446187","url":null,"abstract":"","PeriodicalId":517764,"journal":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"67 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140705096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-14DOI: 10.1109/icassp48485.2024.10447989
Jilu Jin, Xueqin Luo, Gongping Huang, Jingdong Chen, J. Benesty
{"title":"Beamforming Through Online Convex Combination of Differential Beamformers","authors":"Jilu Jin, Xueqin Luo, Gongping Huang, Jingdong Chen, J. Benesty","doi":"10.1109/icassp48485.2024.10447989","DOIUrl":"https://doi.org/10.1109/icassp48485.2024.10447989","url":null,"abstract":"","PeriodicalId":517764,"journal":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"215 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140704393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-14DOI: 10.1109/icassp48485.2024.10446954
Ziming Liu, E. Malis, Philippe Martinet
Stereo matching is one of the low-level visual perception tasks. Currently, two-stage 2D-3D networks and three-stage recurrent networks dominate deep stereo matching. These methods build a cost volume with low-resolution stereo feature maps, which splits the network into a feature net and a matching net. However, the 2D feature map is not uncontrollable, and the low-resolution feature map has lost important matching information. To overcome these problems, we pro-pose the first one-stage 2D-3D deep stereo network, named StereoOne. It has an efficient module that builds a cost volume at image resolution in real-time. The feature extraction and matching are learned in a single 3D network. According to the experiments, the new network can easily surpass the 2D-3D network baseline and it can achieve competitive performance with the state-of-the-art.
{"title":"One-Stage Deep Stereo Network","authors":"Ziming Liu, E. Malis, Philippe Martinet","doi":"10.1109/icassp48485.2024.10446954","DOIUrl":"https://doi.org/10.1109/icassp48485.2024.10446954","url":null,"abstract":"Stereo matching is one of the low-level visual perception tasks. Currently, two-stage 2D-3D networks and three-stage recurrent networks dominate deep stereo matching. These methods build a cost volume with low-resolution stereo feature maps, which splits the network into a feature net and a matching net. However, the 2D feature map is not uncontrollable, and the low-resolution feature map has lost important matching information. To overcome these problems, we pro-pose the first one-stage 2D-3D deep stereo network, named StereoOne. It has an efficient module that builds a cost volume at image resolution in real-time. The feature extraction and matching are learned in a single 3D network. According to the experiments, the new network can easily surpass the 2D-3D network baseline and it can achieve competitive performance with the state-of-the-art.","PeriodicalId":517764,"journal":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"128 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140704475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-14DOI: 10.1109/icassp48485.2024.10446533
Jianfei Jiang, Mingwei Cao, Jun Yi, Chenglong Li
{"title":"DI-MVS: Learning Efficient Multi-View Stereo With Depth-Aware Iterations","authors":"Jianfei Jiang, Mingwei Cao, Jun Yi, Chenglong Li","doi":"10.1109/icassp48485.2024.10446533","DOIUrl":"https://doi.org/10.1109/icassp48485.2024.10446533","url":null,"abstract":"","PeriodicalId":517764,"journal":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"225 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140704566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-14DOI: 10.1109/icassp48485.2024.10448197
Ruicheng Niu, Ziyuan Zhu, Chaofei Li, Dan Meng
{"title":"Search Robust and Adaptable Architecture","authors":"Ruicheng Niu, Ziyuan Zhu, Chaofei Li, Dan Meng","doi":"10.1109/icassp48485.2024.10448197","DOIUrl":"https://doi.org/10.1109/icassp48485.2024.10448197","url":null,"abstract":"","PeriodicalId":517764,"journal":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"224 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140704594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-14DOI: 10.1109/icassp48485.2024.10446726
Fumiki Yohena, Kohei Yatabe
{"title":"Single-Channel Blind Dereverberation Based on Rank-1 Matrix Lifting in Time-Frequency Domain","authors":"Fumiki Yohena, Kohei Yatabe","doi":"10.1109/icassp48485.2024.10446726","DOIUrl":"https://doi.org/10.1109/icassp48485.2024.10446726","url":null,"abstract":"","PeriodicalId":517764,"journal":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"220 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140704629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-14DOI: 10.1109/icassp48485.2024.10446781
Jie Yan, Quan Liu, Lihua Zhang
{"title":"Offline Reinforcement Learning Based on Next State Supervision","authors":"Jie Yan, Quan Liu, Lihua Zhang","doi":"10.1109/icassp48485.2024.10446781","DOIUrl":"https://doi.org/10.1109/icassp48485.2024.10446781","url":null,"abstract":"","PeriodicalId":517764,"journal":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140704778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：